Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    App component names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    й
    0.57
     coraz
    0.51
     পরিষেবা
    0.48
    ट
    0.48
    หัว
    0.47
     versão
    0.46
     सपोर्ट
    0.46
    ch
    0.46
    ഗ്ര
    0.46
    ین
    0.46
    POSITIVE LOGITS
     is
    0.46
     doll
    0.45
     dolls
    0.41
     twee
    0.40
     Oo
    0.40
    檩
    0.40
     Another
    0.40
     another
    0.40
    arelli
    0.39
    вени
    0.39
    Act Density 0.022%

    No Known Activations